Contact Us Copyright Privacy Accessibility Freedom of Information Act

These optional datasets are configured for the 2012 and later versions of MetaMap, so they will not work with releases of MetaMap prior to 2012 unless otherwise specified. See the documentation on "Using Additional Datasets with Public MetaMap" for information on installing optional datasets.

A description of the contents of the Default (USAbase) and Optional Datasets is available on the "Description of MetaMap Data Versions" page. Other DataSets including 2006, 1999, and non-UMLS data sets are listed on the Optional DataSets Page.

Covid-19/SARS-CoV-2 Strings in the 2020AA and Later DataSets

A note about the inclusion of Covid-19/SARS-Cov-2 strings in the 2020AA and later data sets

2020 Specialist Lexicon

The 2020 DB Lexicon is needed for the following 2020 Linux and Mac OS/X datasets.

2020AB UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2020AB UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2020AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2020AB UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2020AA UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2020AA UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2020AA USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2020AA UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2019 Specialist Lexicon

The 2019 DB Lexicon is needed for the following 2019 Linux and Mac OS/X datasets.

2019AB UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2019AB UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2019AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2019AB UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2019AA UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2019AA UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2019AA USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2019AA UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2018 Specialist Lexicon

The 2018 DB Lexicon is needed for the following 2018 Linux and Mac OS/X datasets.

2018AB UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2018AB UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2018AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2018AB UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2018AA UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2018AA UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2018AA USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2018AA UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2017 Specialist Lexicon

The 2017 DB Lexicon is needed for the following 2017 Linux and Mac OS/X datasets.

2017AB UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2017AB UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2017AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2017AB UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2017AA UMLS Base Datasets

This dataset includes all and only sources of Restriction Category 0. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2017AA UMLS USAbase Datasets

This dataset includes the Base vocabularies (those with Restriction Category 0), plus the five Category-4 sources and the four Category-9 sources (including SNOMEDCT). See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.

Note: The the 2017AA USAbase Strict and Base Data Sets are supplied in the MetaMap 2017 Main Distribution.

Linux and Mac OS/X Datasets

2017AA UMLS NLM Datasets

The NLM data version includes the full Metathesaurus. Dataset versions prior to 2015AA of the NLM model excluded the CPT, CPTSP, HCPT, and MTHCH vocabularies from the CPT family, and the HCDT, HCPCS, and MTHHH vocabularies from the HCPCS family. See also, MetaMap FAQ: MetaMap's Base, USAbase, and NLM Data Versions.
Linux and Mac OS/X Datasets

2016 Specialist Lexicon

The 2016 DB Lexicon is needed for the following 2016AA and 2016AB Linux and Mac OS/X datasets.

2016AB UMLS Base Datasets

Linux and Mac OS/X Datasets

2016AB UMLS USAbase Datasets

Linux and Mac OS/X Datasets

2016AB UMLS NLM Datasets

Linux and Mac OS/X Datasets

2016AA UMLS Base Datasets

Linux and Mac OS/X Datasets

2016AA UMLS USAbase Datasets

Note: The the 2016AA USAbase Strict and Base Data Sets are supplied in the MetaMap 2016 Main Distribution.
Linux and Mac OS/X Datasets

2016AA UMLS NLM Datasets

Linux and Mac OS/X Datasets

2015 Specialist Lexicon

The 2015 DB Lexicon is needed for the following 2015AA and 2015AB Linux and Mac OS/X datasets. The checksums for the DB Lexicon archive are: [sha1sum] [md5sum] .

The Lexicon is included in Windows DataSets.

2015AB UMLS Base Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2015AB UMLS USAbase Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2015AB UMLS NLM Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2015AA UMLS Base Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2015AA UMLS USAbase Datasets

Linux and Mac OS/X Datasets

2015AA UMLS NLM Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2014AB UMLS Base Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2014AB UMLS USAbase Datasets

Note: The the 2014AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2014 Main Distribution.
Linux and Mac OS/X Datasets

2014AB UMLS NLM Datasets

Linux and Mac OS/X Datasets

2014AA UMLS Base Datasets

Linux and Mac OS/X Datasets

2014AA UMLS USAbase Datasets

Note: The the 2014AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2014 Main Distribution.
Linux and Mac OS/X Datasets

2014AA UMLS NLM Datasets

Linux and Mac OS/X Datasets

2013AB UMLS Base Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2013AB UMLS USAbase Datasets

Note: The the 2013AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2013v2 Main Distribution.
Windows Datasets
Linux and Mac OS/X Datasets

2013AB UMLS NLM Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2013AA UMLS Base Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2013AA UMLS USAbase Datasets

Note: The the 2013AB USAbase Strict and Base Data Sets are supplied in the MetaMap 2013 Main Distribution.
Windows Datasets
Linux and Mac OS/X Datasets

2013AA UMLS NLM Datasets

Windows Datasets
Linux and Mac OS/X Datasets

2013 Specialist Lexicon

Only required for users who have installed MetaMap 2012 and earlier, and have installed the 2013v2 binary distribution. Note, this is included in MetaMap 2013v2 Main Distribution. Works with MetaMap 2013v2 through 2011.
2013 Specialist Lexicon (C and DB Versions) for MetaMap (Bzip2 Tar - 40 MB). [sha1sum] [md5sum]
2013 Specialist Lexicon (C and DB Versions) for MetaMap (WinZip ~ 40 MB). [sha1sum] [md5sum]
2013 Specialist Lexicon (C and DB Versions) for MetaMap (7Zip ~ 40 MB). [sha1sum] [md5sum]
Additional configuration is needed to use the 2013 DB Lexicon, links to DB lexicon files must be added to any existing datasets, This is not required if you want to use the C Lexicon: 
	       $ cd public_mm/DB/DB.{umlssubset}.{year}{release}.{model}
	       $ ln -s ../../lexicon/data/2013/* .
For Example: 
	       $ cd public_mm/DB/DB.USAbase.2013AA.strict
	       $ ln -s ../../lexicon/data/2013/* .
The lexicon files must be copied on Windows XP/7: 
	       D:\workspace> cd public_mm\DB\DB.{umlssubset}.{year}{release}.{model}
	       D:\workspace> copy ..\..\lexicon\data\2013\* .

Additional DataSets are available; these are listed on /nfsvol/cgsb_share2/ind/ind1/ind_repository the Optional DataSets Page.